volume-12-Issue 1 (2020)
JUSPN, volume-12, Issue 1 (2020) , PP 25 - 30
Published: 25 Jan 2020
by Hardik Manek , Nikhil Kataria , Sujai Jain , Chitra Bhole from Acadia University, Wolfville, Nova Scotia, Canada, NS B4P 2R6 K.J.S.I.E.I.T, Mumbai, India, 400022
Abstract: Cashless payments have become effortless with the advent of new technology and the internet. But, for online transactions, you don't have to be in a certain place where the transaction occurs, making it vulnerable to fraudulent attacks. A cyber-attacker can pretend to be the owner of a credit card and make a fraudulent transaction. There are several techniques to determine the nature of the transaction, for instance, by comparing the current transaction with previous transactions. If the monetary difference between current transaction and previous transaction is too large, then there is a greater probability of current transaction being a fraudulent transaction. This method is not reliable for anomaly detection. In some countries like India and China, banks deploy a two-step verification process which strengthens the security of the transaction. While in other countries, employees in the bank manually segregate the transactions to be fraud or not. These methods are highly dependent on human intervention. Machine Learning can be utilized to automate the process of anomaly detection. Supervised algorithms such as Logistic Regression can be used to build a model that will predict the output in the form of binary classes i.e., 0 for a valid transaction and 1 for a fraudulent transaction. Autoencoder Neural Network is one of the unsupervised algorithms using which better accuracy can be obtained for anomaly detection. In this paper, we explain different machine learning algorithms viz Hidden Markov Model, Artificial Neural Network, and Convolutional Neural Network. Moreover, Logistic Regression is implemented, and the results obtained are highlighted read more... read less...
Keywords: Credit Card Fraud, Neural Network, Cashless Transaction
JUSPN, volume-12, Issue 1 (2020) , PP 17 - 24
Published: 24 Jan 2020
by Tomáš Pikulíka , Peter Štarchoňb from Faculty of Management, Comenius University in Bratislava Odbojárov 10, 820 05 Bratislava 25, Slovakia
Abstract: Pressure for effectivity of interconnection of personal data with digital accounts eliminates paperbased personal data processing (PDP). The objective of this paper is to reveal weak pots of transfer and PDP in Wi-Fi ready mobile devices. Purpose is to reveal the set of principles for data transfer and storage of personal data in ubiquitous and pervasive network environment. Our scope is to point out the recommendation for organization (data controller) in managing data transfer procedure to prevent incidents and personal data misusage and set preventive action plan for individuals (data subject) to protect their digital accounts. The contribution of our paper is a set of recommendations that sum up principles for secure PDP that should skip individual action of data subject. The paper concludes by arguing that organization (data controller) need to manage PDP requirements and individuals (data subject) could set preventive action to protect their digital accounts. These findings provide a potential mechanism for prevent personal data - GDPR compliant methods like pseudonymization and encryption. read more... read less...
Keywords: Data transfer, data privacy, pseudonymization, encryption, GDPR, ePrivacy
JUSPN, volume-12, Issue 1 (2020) , PP 09 - 15
Published: 17 Jan 2020
by Mohamed TALHA, Nabil ELMARZOUQI, Anas ABOU EL KALAM from ENSA UCA, Marrakesh, Morocco, 40000
Abstract: Quality and Security are two major issues in Big Data that pose many challenges. High volume, heterogeneity and high speed of data generation and processing are, amongst others, common challenges that must be addressed before setting up any data quality management system or data security system. This document provides an overview of data quality and data security in a Big Data context and highlights the conflicts that may exist during the implementation of these systems. Such a conflict makes the setting up of such systems even more complex and the reflection into new solutions becomes a major prerequisite. In this paper, we consider these challenges to present a global solution to evaluate the quality of data without impacting data security and without it becoming a barrier. read more... read less...
Keywords: Big Data, Data Quality, Data Security, Accuracy Assessment, Record Linkage, Big Data Sampling
Performance Testing for VoIP Emergency Services: a Case Study of the EMYNOS Platform and a Reflection on potential Blockchain Utilisation for NG112 Emergency Communication
JUSPN, volume-12, Issue 1 (2020) , PP 01 - 08
Published: 12 Jan 2020
by Budankailu Sameer Kumar Subudhi, Faruk Catal, Nikolay Tcholtchev, Kin Tsun Chiu, Yacine Rebahi, Michell Boerger and Philipp Lämmel from Fraunhofer FOKUS, Kaiserin-Augusta-Allee 31, Berlin, 10589, Germany
Abstract: VoIP-based emergency communication is a promising approach to improving the safety of citizens worldwide. The transition required in this scope includes substituting the legacy PSTN/SS7 based emergency call system by Next Generation IP based components for call establishment and control. Thereby, SIP is used as a session control protocol and RTP as the means to transfer emergency data between the caller and the corresponding Public Safety Access Point (PSAP). The emergency data is not only restricted to voice communication but can cover a rich variety of data, which can be acquired by different means (including the end-user devices) and transmitted over IP. This includes video, geo- positioning data, voice, Real-Time Text, and sensor data in line with emerging IoT architectures and approaches. A vital aspect in this scope is given by the performance of the underlying network, including its capability to establish calls in emergencies and to transfer the data required for serving the situation. Therefore, in this paper, we evaluate the computational performance of the most recent VoIP emergency system implementation, which was developed by the H2020-EMYNOS project as a realisation of the EENA NG112 Long Term Definition (LTD) vision. We perform a series of trials and evaluate the performance of the EMYNOS system in a multi-party lab environment established during the project. We evaluate the time needed to perform basic emergency call operations over IP, whilst in parallel generating Internet type of background traffic. Correspondingly, we worked out a methodology and implemented it in our testbed, both of which are presented in the current paper. The obtained numerical results lead to the conclusion that SIP-based emergency services stand a good chance to replace legacy systems when it comes to their performance. Additionally, we also provide a perspective on how the blockchain technology could potentially be put to use to enhance the quality of the next-generation emergency services. We propose the utilisation of blockchain technology for tracking emergency calls and enabling efficient recognition of fraud calls, which is a critical aspect for PSAP providers concerning the potential denial of service attacks. In this context, we provide evaluations and numerical results based on a private Ethereum based blockchain playground running at the premises of Fraunhofer FOKUS. read more... read less...
Keywords: performance testing; SIP, VoIP, NG112, PSAP, NGN, background traffic, blockchain, fraud-detection